2026-09-19T16:21:49Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1432562022-06-16T03:46:04Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Rus, Daniela
Shubert, Ryan
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-06-15T13:07:41Z
2022-06-15T13:07:41Z
2022-02
2022-02-22T18:32:08.377Z
https://hdl.handle.net/1721.1/143256
In this paper, we present FlightMARL, an extension of the Flightmare simulator that implements a modular multi-agent reinforcement learning engine capable of supporting an array of models and algorithms. We explore representation learning of various different models in this environment. We implement recurrent agents as both discrete and continuous networks. We evaluate the learned representations of the models in the multi-agent environment. We demonstrate that agents constructed from continuous-time neural networks achieve interpretable causality in their representations.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
FlightMARL: A Multi-Agent Reinforcement Learning Framework for Vision-Based Control of Autonomous Quadrotors
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="3604597d-f35a-4909-b9be-4ab30ee67507">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>FlightMARL: A Multi-Agent Reinforcement Learning Framework for Vision-Based Control of Autonomous Quadrotors</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Shubert, Ryan</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>In this paper, we present FlightMARL, an extension of the Flightmare simulator that implements a modular multi-agent reinforcement learning engine capable of supporting an array of models and algorithms. We explore representation learning of various different models in this environment. We implement recurrent agents as both discrete and continuous networks. We evaluate the learned representations of the models in the multi-agent environment. We demonstrate that agents constructed from continuous-time neural networks achieve interpretable causality in their representations.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>